Borrowing Knowledge From Pre-trained Language Model: A New Data-efficient Visual Learning Paradigm
Wenxuan Ma, Shuang Li, Jinming Zhang, Chi Harold Liu, Jingxuan Kang, Yulin Wang, Gao Huang
Abstract
The development of vision models for real-world applications is hindered by the challenge of annotated data scarcity, which has necessitated the adoption of dataefficient visual learning techniques such as semi-supervised learning. Unfortunately, the prevalent cross-entropy supervision is limited by its focus on category discrimination while disregarding the semantic connection between concepts, which ultimately results in the suboptimal exploitation of scarce labeled data. To address this issue, this paper presents a novel approach that seeks to leverage linguistic knowledge for data-efficient visual learning. The proposed approach, BorLan, Borrows knowledge from off-theshelf pretrained Language models that are already endowed with rich semantics extracted from large corpora, to compensate the semantic deficiency due to limited annotation in visual training. Specifically, we design a distribution alignment objective, which guides the vision model to learn both semantic-aware and domain-agnostic representations for the task through linguistic knowledge. One significant advantage of this paradigm is its flexibility in combining various visual and linguistic models. Extensive experiments on semi-supervised learning, single domain generalization and few-shot learning validate its effectiveness. Code is available at https://github.com/BIT-DA/BorLan .
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
6 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- VeCAF: Vision-language Collaborative Active Finetuning with Training Objective Awareness cites Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
- VeCAF: Vision-language Collaborative Active Finetuning with Training Objective Awareness cites Learning Transferable Visual Models From Natural Language Supervision
- UNIALIGN: Scaling Multimodal Alignment within One Unified Model cites A ConvNet for the 2020s
- UNIALIGN: Scaling Multimodal Alignment within One Unified Model cites Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
- UNIALIGN: Scaling Multimodal Alignment within One Unified Model cites Learning Transferable Visual Models From Natural Language Supervision
- A ConvNet for the 2020s cites Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
- Language-Assisted Debiasing and Smoothing for Foundation Model-Based Semi-Supervised Learning cites Learning Transferable Visual Models From Natural Language Supervision
- Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision cites A Simple Framework for Contrastive Learning of Visual Representations
- Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision cites Learning Transferable Visual Models From Natural Language Supervision
- Swin Transformer: Hierarchical Vision Transformer using Shifted Windows cites Learning Transferable Visual Models From Natural Language Supervision
- Learning Transferable Visual Models From Natural Language Supervision cites A Simple Framework for Contrastive Learning of Visual Representations
- Learning Modality Knowledge Alignment for Cross-Modality Transfer cites Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
- Learning Modality Knowledge Alignment for Cross-Modality Transfer cites Learning Transferable Visual Models From Natural Language Supervision
Cited by top-tier papers6
- Learning Modality Knowledge Alignment for Cross-Modality TransferWenxuan Ma, Shuang Li, Lincan Cai, Jingxuan KangICML 2024 · 10 citations
- VeCAF: Vision-language Collaborative Active Finetuning with Training Objective AwarenessRongyu Zhang, Zefan Cai, Huanrui Yang, Zidong Liu et al.ACM MM 2024 · 5 citations
- PLMTrajRec: A Scalable and Generalizable Trajectory Recovery Method with Pre-trained Language ModelsTonglong Wei, Yan Lin, Youfang Lin, Shengnan Guo et al.NeurIPS 2025 · 3 citations
- UNIALIGN: Scaling Multimodal Alignment within One Unified ModelBo Zhou, Liulei Li, Yujia Wang, Huafeng Liu et al.CVPR 2025
- Language-Assisted Debiasing and Smoothing for Foundation Model-Based Semi-Supervised LearningNa Zheng, Xuemeng Song, Xue Dong, Aashish Nikhil Ghosh et al.CVPR 2025
Builds on30
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
- Swin Transformer: Hierarchical Vision Transformer using Shifted WindowsZe Liu, Yutong Lin, Yue Cao, Han Hu et al.ICCV 2021 · 31,683 citations
- A Simple Framework for Contrastive Learning of Visual RepresentationsTing Chen, Simon Kornblith, Mohammad Norouzi, Geoffrey E. HintonICML 2020 · 24,064 citations
- A ConvNet for the 2020sZhuang Liu, Hanzi Mao, Chao-Yuan Wu, Christoph Feichtenhofer et al.CVPR 2022 · 6,782 citations
- Scaling Up Visual and Vision-Language Representation Learning With Noisy Text SupervisionChao Jia, Yinfei Yang, Ye Xia, Yi-Ting Chen et al.ICML 2021 · 5,401 citations
Related papers
- Fine-Grained Visual Prompt Learning of Vision-Language Models for Image RecognitionHongbo Sun, Xiangteng He, Jiahuan Zhou, Yuxin PengACM MM 2023 · 16 citations
- Training Spatial-Frequency Visual Prompts and Probabilistic Clusters for Accurate Black-Box Transfer LearningWonwoo Cho, Kangyeol Kim, Saemee Choi, Jaegul ChooACM MM 2024
- Data-Efficient Language Shaped Few-shot Image ClassificationZhenwen Liang, Xiangliang ZhangEMNLP Findings 2021
- Language Does Matter for Cross-Domain Few-Shot Visual Feature EnhancementFei Zhou, Xiwen Zhang, Qingqing Qiu, Lei Zhang et al.CVPR 2026
- Semi-Supervised CLIP Adaptation by Enforcing Semantic and Trapezoidal ConsistencyKai Gan, Bo Ye, Min-Ling Zhang, Tong WeiICLR 2025
